Improving and accelerating materials development is an important goal in science and industry, as tailored and optimized materials are key to innovation. With recent advances in modeling, simulation, and machine learning, tailoring the chemical composition and the microstructure of materials to a targeted property has become feasible. Beyond improving the performance of materials, this allows us to explore how to adapt materials to recycling requirements. It opens up pathways to mitigate negative effects of contamination and to avoid issues with availability and sustainability of critical elements. This inverse design process requires computational techniques to characterize and reconstruct the materials’ microstructures and to quantify and model the mechanical response at the microscale. Computational homogenization of these microstructures then allows for an automated prediction and understanding of the interplay between microstructural features and effective properties. To describe the nonlinear, inelastic effective behavior of materials with high precision while explicitly considering design variables, suitable machine learning approaches incorporating knowledge from fundamental underlying physics enable an improved extrapolation capability and the use of sparse training data obtained from computational homogenization. Beyond constitutive modeling, data analysis and machine learning help to exploit knowledge from simulations in terms of surrogate models and are therefore key to the exploration and prediction of process-structure-property linkages as well as for inverse design. Topics of interest covered within this mini-symposium include but are not limited to: - techniques for exploration and inversion of process-structure-property linkages, - inverse design of heterogeneous materials from metals to architected materials, - approaches that improve recyclability or sustainability through data-driven design, - design approaches that account for constraints e.g., related to manufacturing processes, - data-driven multiscale simulations including microstructure characterization and reconstruction, e.g., 2D and 3D image-based methods, definition of descriptors.